COMPMID-1632 Add CLL2NormalizationLayer for NHWC and FP32

Change-Id: Iae22554d5fe893fd22a000eab5bfd8275ea06eb3
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/154102
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLReductionOperationKernel.h b/arm_compute/core/CL/kernels/CLReductionOperationKernel.h
index ef24fd5..b5b90a1 100644
--- a/arm_compute/core/CL/kernels/CLReductionOperationKernel.h
+++ b/arm_compute/core/CL/kernels/CLReductionOperationKernel.h
@@ -50,7 +50,7 @@
 
     /** Set the input and output tensors.
      *
-     * @param[in]  input  Source tensor. Data types supported: QASYMM8/F16/F32. Data layouts supported: NCHW.
+     * @param[in]  input  Source tensor. Data types supported: QASYMM8/F16/F32.
      * @param[out] output Destination tensor. Data types and data layouts supported: Same as @p input.
      *                    Output will have the same number of dimensions as input.
      * @param[in]  axis   Axis along which to reduce. Supported reduction axis : 0,1,2,3
@@ -61,7 +61,7 @@
 
     /** Static function to check if given info will lead to a valid configuration of @ref CLReductionOperationKernel.
      *
-     * @param[in] input  Source tensor info. Data types supported: QASYMM8/F16/F32. Data layouts supported: NCHW.
+     * @param[in] input  Source tensor info. Data types supported: QASYMM8/F16/F32.
      * @param[in] output Destination tensor info. Data types and data layouts supported: Same as @p input.
      *                   Output will have the same number of dimensions as input.
      * @param[in] axis   Axis along which to reduce. Supported reduction axis : 0,1,2,3
diff --git a/arm_compute/runtime/CL/functions/CLL2NormalizeLayer.h b/arm_compute/runtime/CL/functions/CLL2NormalizeLayer.h
index d3d34f8..86ccd34 100644
--- a/arm_compute/runtime/CL/functions/CLL2NormalizeLayer.h
+++ b/arm_compute/runtime/CL/functions/CLL2NormalizeLayer.h
@@ -53,18 +53,18 @@
 
     /** Set the input and output tensors.
      *
-     * @param[in]  input   Source tensor. Data types supported: F32. Data layouts supported: NCHW.
+     * @param[in]  input   Source tensor. Data types supported: F32. Data layouts supported: NCHW/NCHW.
      * @param[out] output  Destination tensor. Data types and data layouts supported: Same as @p input.
-     * @param[in]  axis    Axis along which to reduce. Supported reduction axis : 0
+     * @param[in]  axis    Axis along which to reduce. Supported reduction axis : 0, 2
      * @param[in]  epsilon (Optional) Lower bound value for the normalization.
      */
     void configure(ICLTensor *input, ICLTensor *output, unsigned int axis, float epsilon = 1e-12);
 
     /** Static function to check if given info will lead to a valid configuration of @ref CLL2NormalizeLayer.
      *
-     * @param[in] input   Source tensor info. Data types supported: F32. Data layouts supported: NCHW.
+     * @param[in] input   Source tensor info. Data types supported: F32. Data layouts supported: NCHW/NCHW.
      * @param[in] output  Destination tensor info. Data types and data layouts supported: Same as @p input.
-     * @param[in] axis    Axis along which to reduce. Supported reduction axis : 0
+     * @param[in] axis    Axis along which to reduce. Supported reduction axis : 0, 2,
      * @param[in] epsilon (Optional) Lower bound value for the normalization.
      *
      * @return a status
diff --git a/arm_compute/runtime/CL/functions/CLReductionOperation.h b/arm_compute/runtime/CL/functions/CLReductionOperation.h
index 4208178..ac35b7b 100644
--- a/arm_compute/runtime/CL/functions/CLReductionOperation.h
+++ b/arm_compute/runtime/CL/functions/CLReductionOperation.h
@@ -53,18 +53,18 @@
 
     /** Set the input and output tensors.
      *
-     * @param[in]  input  Source tensor. Data types supported: QASYMM8/F16/F32. Data layouts supported: NCHW.
+     * @param[in]  input  Source tensor. Data types supported: QASYMM8/F16/F32.
      * @param[out] output Destination tensor. Data types and data layouts supported: Same as @p input.
-     * @param[in]  axis   Axis along which to reduce. Supported reduction axis : 0
+     * @param[in]  axis   Axis along which to reduce. Supported reduction axis : 0, 1, 2, 3
      * @param[in]  op     Reduction operation to perform.
      */
     void configure(ICLTensor *input, ICLTensor *output, unsigned int axis, ReductionOperation op);
 
     /** Static function to check if given info will lead to a valid configuration of @ref CLReductionOperation.
      *
-     * @param[in] input  Source tensor info. Data types supported: QASYMM8/F16/F32. Data layouts supported: NCHW.
+     * @param[in] input  Source tensor info. Data types supported: QASYMM8/F16/F32.
      * @param[in] output Destination tensor info. Data types and data layouts supported: Same as @p input.
-     * @param[in] axis   Axis along which to reduce. Supported reduction axis : 0
+     * @param[in] axis   Axis along which to reduce. Supported reduction axis : 0, 1, 2, 3
      * @param[in] op     Reduction operation to perform.
      *
      * @return a status